Indirect Standardization and the Standardized Mortality Ratio

Comparing a population's deaths with the deaths a standard set of age-specific rates would produce. Expected deaths, the standardized mortality ratio as a weighted average of age-specific ratios, the indirectly standardized rate and the comparative mortality figure, worked for Maine, Alaska, Florida and Utah against the 2021 U.S. rates; the exact Poisson interval and the log-scale interval for the ratio; why two ratios cannot safely be compared with each other, while ratios of directly standardized rates can; and when the direct and the indirect method each apply.

Maine recorded 17,269 deaths in 2021 and Alaska 6,208. How many deaths would each state have had if its residents had died at the national rates for their ages? Maine would have had 17,261.9 and Alaska 5,854.3. So Maine's mortality was almost exactly what the national rates predict for a population of its ages, and Alaska's was 6% higher. The ratio of observed to expected deaths, 1.0004 for Maine and 1.0604 for Alaska, is the standardized mortality ratio.

This article is about that comparison, indirect standardization. It continues Direct Standardization, which defines the directly standardized rate (DSR), the standard weights $w_i$ and the 2000 U.S. standard population, and works the national examples of 2007 to 2013 and 2010 to 2019 that are referred to below. The notation is the same: $d_i$ deaths in a population $n_i$ in age group $i$, with rates $r_i = d_i/n_i$. The exact limits for a Poisson count come from Crude Rates and Their Precision.

First we define expected deaths, the standardized mortality ratio and the indirectly standardized rate. Then we compare Maine, Alaska, Florida and Utah with the United States, and set the result beside the ratio of directly standardized rates. Next we put a confidence interval on the ratio, and see why two such ratios cannot safely be compared with each other. Finally we say when each of the two methods is the right one.

Indirect standardization

Direct standardization, the subject of the previous article, needs the age-specific death counts of every population compared. For many populations these are unavailable or too small to trust: a county, an occupational group, a cohort of workers exposed to a chemical. Indirect standardization needs only two things from the study population, its total number of deaths and its age structure. It also needs a set of standard age-specific rates $R_i$ from a large reference population.

Here is the idea in one sentence. Ask how many deaths the study population would have had at the standard rates, given its own ages, and compare that with how many it actually had.

The expected deaths are the deaths the study population would have if it experienced the standard rates at every age:

$$E = \sum_i n_i R_i.$$

The standardized mortality ratio compares the deaths observed, $O = \sum_i d_i$, with this expectation:

$$\text{SMR} = \frac{O}{E}.$$

An SMR of 1.10 means 10% more deaths than the standard rates predict for a population of that age structure. Multiplying by the standard population's crude rate $R_s$ gives the indirectly standardized rate, $\text{ISR} = \text{SMR} \times R_s$ (Anderson and Rosenberg, 1998, Technical notes, equations 4 and 5).

Breslow and Day (1987, §2.3) trace the SMR to the eighteenth century, and its use for comparing occupations to Farr, in the Registrar General's report of 1855. They also show that it is a weighted average of the age-specific ratios $r_i/R_i$, with weights equal to the expected deaths $e_i = n_i R_i$:

$$\frac{\sum_i e_i (r_i/R_i)}{\sum_i e_i} = \frac{\sum_i n_i r_i}{E} = \frac{O}{E}.$$

Suppose the study population's rates are a constant multiple $\theta$ of the standard rates. Then every ratio is $\theta$ and the SMR estimates it. These weights are the ones that minimize the variance of the estimate (Breslow and Day, 1987, §2.3).

Maine and Alaska against the United States

NCHS publishes each state's total deaths, but this article's data do not include deaths by age for the states. So the four states are compared by indirect standardization. The standard is the 2021 U.S. age-specific rates (Murphy et al., 2024, Table 2), applied to the Census estimates of each state's population by age.

For Maine, the expected deaths by age group, from under 1 to 85 and over, are

$$62.9,\ 12.8,\ 20.4,\ 137.3,\ 301.3,\ 475.8,\ 907.0,\ 2{,}383.2,\ 3{,}939.9,\ 4{,}303.2,\ 4{,}718.1,$$

summing to $E = 17{,}261.9$. Maine recorded $O = 17{,}269$ deaths, so $\text{SMR} = 17{,}269/17{,}261.9 = 1.0004$. For Alaska, the expected deaths are

$$51.6,\ 9.7,\ 14.7,\ 85.2,\ 205.4,\ 292.6,\ 441.6,\ 1{,}009.6,\ 1{,}429.0,\ 1{,}254.2,\ 1{,}060.8,$$

summing to $E = 5{,}854.3$ against $O = 6{,}208$ observed, so $\text{SMR} = 1.0604$. Maine's mortality was what the national rates predict for a population of its ages; Alaska's was 6% higher. These are the predictions Crude Rates and Their Precision made from the same national rates.

State Observed Expected SMR Exact 95% interval ISR DSR / U.S. DSR
Maine 17,269 17,261.9 1.0004 (0.9855, 1.0154) 1,044.2 1.0110
Alaska 6,208 5,854.3 1.0604 (1.0342, 1.0871) 1,106.8 1.0583
Florida 261,369 279,888.5 0.9338 (0.9303, 0.9374) 974.7 0.9468
Utah 22,569 24,973.7 0.9037 (0.8920, 0.9156) 943.3 0.9274

The indirectly standardized rates multiply each SMR by the U.S. crude rate in 2021, 1,043.8 per 100,000. They are on the scale of that crude rate rather than of the 2000 standard.

The last column divides each state's published adjusted rate by the U.S. adjusted rate, 879.7. Breslow and Day (1987, §2.3) call this ratio of directly standardized rates the comparative mortality figure (CMF). The SMR and the CMF tell the same story for every state, as Breslow and Day observe they usually do in practice. They never differ here by more than 0.025.

Example (what an SMR of 1 does not show). Maine's SMR is 1.0004, and its exact interval contains 1, but that does not show that Maine's death rates matched the nation's at every age. Here is what the SMR does say. Maine's crude death rate was 21% above the nation's (1,258.4 against 1,043.8). The SMR says that the whole of that excess is accounted for by its age structure: for a population of its ages, Maine recorded almost exactly the deaths the national rates predict.

But the SMR is an average of Maine's age-specific ratios $r_i/R_i$, weighted by its expected deaths, and three quarters of those fall at ages 65 and over. A ratio above 1 at some ages can offset one below 1 at others. Nor does an interval that contains 1 show that the true ratio is 1. It shows only that random variation cannot tell it from 1, at a precision of about 1.5% either way.

The CMF averages the same ratios with different weights. Its weights are the deaths the 2000 standard population would have at the national rates ($w_i R_i$ in place of $n_i R_i$), by the same algebra as for the SMR:

$$\text{CMF} = \frac{\sum_i w_i r_i}{\sum_i w_i R_i} = \frac{\sum_i (w_i R_i)\,(r_i/R_i)}{\sum_i w_i R_i}.$$

It puts Maine 1.1% above the nation.

A confidence interval for the SMR

Where did the exact intervals in the table come from? The idea is to treat the standard rates as fixed, which is reasonable when the standard population is much larger than the study population. Then $E$ is a constant and all the random variation is in $O$, a Poisson count. An interval for its mean, divided by $E$, is an interval for the SMR. Breslow and Day (1987, §2.3) use the exact Poisson limits. With the gamma quantiles of Crude Rates and Their Precision,

$$\text{SMR}_L = \frac{G^{-1}_{O}(0.025)}{E}, \qquad \text{SMR}_U = \frac{G^{-1}_{O+1}(0.975)}{E}.$$

On the scale of the SMR itself, $E$ is a constant, so $\operatorname{Var}(\text{SMR}) = \operatorname{Var}(O)/E^2$, estimated by $O/E^2$. The standard error is $\sqrt{O}/E = \text{SMR}/\sqrt{O}$, the relative standard error $1/\sqrt{O}$ of a single count.

A simpler approximation than the exact limits uses $\operatorname{SE}(\log \text{SMR}) = 1/\sqrt{O}$ (Breslow and Day, 1987, equation 2.9), giving $\text{SMR} \times e^{\pm 1.96/\sqrt{O}}$. It is the delta-method result of Crude Rates and Their Precision for the log of a Poisson count: $\log \text{SMR} = \log O - \log E$, with $\operatorname{Var}(\log O) \approx 1/O$. For the states, with thousands of deaths, the two agree to three decimals; for Alaska the log-scale interval is (1.0344, 1.0871). Neither interval for Maine excludes 1. Alaska's, Florida's and Utah's do.

For small counts they diverge. Suppose an occupational cohort records 12 deaths from some cause where the standard rates predict 7.5. The SMR is 1.60. The exact interval is (0.827, 2.795) and the log-scale interval (0.909, 2.817), with the lower limit too high. Breslow and Day (1987, Example 2.8) find the same weakness in the log-scale lower limit. The exact one-sided probability of 12 or more deaths when 7.5 are expected is 0.0792. Doubling it, the two-sided exact test of $\text{SMR} = 1$ gives $p = 0.158$, consistent with the exact interval's inclusion of 1.

Comparing SMRs with each other

An SMR compares one population with the standard. Is it safe to compare two populations' SMRs with each other? Less so. Each SMR weights the age-specific ratios by its own population's expected deaths. An older population's SMR is dominated by the ratios at old ages, and a younger one's by those at younger ages.

Breslow and Day (1987, §2.3, Table 2.13) give an example, after Kilpatrick (1963), in which one cohort has the higher death rate at every age and yet the lower SMR. They quote Kilpatrick: "the ratio of two CMFs is a CMF but the ratio of two SMRs is not an SMR". Ratios of directly standardized rates are always weighted averages of the age-specific rate ratios, and so never show this reversal. For two populations A and B with positive rates, standardized to the same weights,

$$\frac{\text{DSR}_A}{\text{DSR}_B} = \frac{\sum_i w_i r_{Ai}}{\sum_i w_i r_{Bi}} = \frac{\sum_i (w_i r_{Bi})\,(r_{Ai}/r_{Bi})}{\sum_i w_i r_{Bi}},$$

an average of the ratios $r_{Ai}/r_{Bi}$ with the nonnegative weights $w_i r_{Bi}$. An average lies between the smallest and the largest of the values averaged, so if A's rate is the higher at every age, every ratio exceeds 1 and so does the ratio of the adjusted rates. For 2013 against 2007, the eleven ratios run from 0.823 to 0.992 and their weighted average is the adjusted ratio, 0.944.

Back to the four states. For Maine and Alaska, the ratio of the SMRs is $1.0004/1.0604 = 0.943$, and the ratio of the published adjusted rates is $889.4/931.0 = 0.955$. For Florida and Utah, the two ratios are 1.033 and 1.021. Both measures agree that Alaska's mortality exceeded Maine's once age is taken into account, the reverse of the crude rates' ratio of 1.485. Both put Florida slightly above Utah.

When age-specific rate ratios are roughly constant across ages, SMRs can be compared. The close agreement of the SMRs and CMFs suggests the ratios are roughly constant here, though the states' age-specific deaths are not in this article's data. When the ratios are not constant, a directly standardized comparison, or the age-specific rates themselves, is the safer basis.

Which method, when

The two methods answer slightly different questions and have complementary weaknesses. Breslow and Day (1987, §2.3(f)) describe the choice as a trade-off between bias and variance.

  • Direct standardization puts every population on the same weights. So its adjusted rates can be compared with each other and across time, and a population with lower rates at every age always has the lower adjusted rate. It needs age-specific deaths for each population, and it becomes unstable when some age groups have few deaths. It is the method of official vital statistics: NCHS's state, national and trend comparisons, and WHO's international ones.
  • Indirect standardization needs only total deaths and the population by age. Its SMR is the minimum-variance estimate of a common rate ratio, so it is stable for small populations. It compares each population with the standard, not with each other, and comparisons of SMRs can mislead when rate ratios vary with age. It is the method of occupational cohorts, small areas and any study population compared with general-population rates.
  • Neither replaces the age-specific rates when those rates move in different directions, as from 2010 to 2019. A single summary of a divergent pattern depends on its weights. Reporting the specific rates alongside the summary shows the reader what it averages.

Age is the usual adjustment variable because it is the strongest influence on most rates. But the arithmetic applies to any variable that divides the populations into strata: sex, race and Hispanic origin, or age and sex together. Adjusting for several variables at once leads to regression models for rates, which Breslow and Day (1987) prefer for analytical work. The library's Logistic Regression treats the corresponding model for proportions.

Summary

Quantity Formula
Comparative mortality figure $\text{DSR}/\text{DSR}_{\text{standard}}$
Expected deaths $E = \sum_i n_i R_i$
Standardized mortality ratio $\text{SMR} = O/E$; exact limits $G^{-1}_{O}(0.025)/E$ and $G^{-1}_{O+1}(0.975)/E$
Indirectly standardized rate $\text{ISR} = \text{SMR} \times R_s$

Worked problems

These two problems are posed on the unit's own data: the simulated population of 5,000 from the worked problems of Direct Standardization, and a small cohort of our own construction. The script named under "In Python" computes every number and asserts the main ones.

Problem 1 (the simulated population by indirect standardization). The first worked problem of Direct Standardization adjusts the death rate of a simulated population of 5,000 with Alaska's age structure, which had 28 deaths in one year. Its adjusted rate is 607.1 per 100,000, against 715.25 for the U.S. rates of 2019 from which it was simulated. For the same 5,000 people, use the U.S. 2019 age-specific rates as the standard. Find the expected deaths, the SMR with its exact interval, the indirectly standardized rate, and the comparative mortality figure.

Solution. The expected deaths by age are the simulation's own expected counts,

$$0.35,\ 0.06,\ 0.09,\ 0.46,\ 1.00,\ 1.38,\ 2.23,\ 5.45,\ 8.00,\ 7.20,\ 6.08,$$

which sum to $E = 32.30$. With $O = 28$ observed,

$$\text{SMR} = \frac{28}{32.30} = 0.867.$$

The exact 95% limits for a count of 28 are $G^{-1}_{28}(0.025) = 18.606$ and $G^{-1}_{29}(0.975) = 40.468$, so the interval for the SMR is $(18.606/32.30,\ 40.468/32.30) = (0.576,\ 1.253)$. It contains 1, the true SMR here, since the population was simulated with exactly the standard rates; an exact interval misses the true value in at most 5% of replicates. The log-scale interval, $0.867 \times e^{\pm 1.96/\sqrt{28}} = (0.599,\ 1.256)$, has a lower limit that is too high, the weakness seen in the cohort example.

The indirectly standardized rate is $0.867 \times 869.7 = 754.0$ per 100,000, on the scale of the 2019 U.S. crude rate. The comparative mortality figure is the ratio of the adjusted rates, $607.1/715.25 = 0.849$. The SMR and the CMF agree on the direction and roughly on the size, 13% and 15% below the standard. They differ because they weight the same age-specific ratios $r_i/R_i$ differently: the SMR by this population's expected deaths $n_i R_i$, the CMF by the standard population's $w_i R_i$. The CMF's weights put 56% on ages 75 and over, the SMR's 41%.

Problem 2 (a small cohort). In a cohort of workers, 3 deaths from a cause are observed where the standard rates predict 1.2. Find the SMR, test whether it differs from 1, and give the exact 95% interval.

Solution. The SMR is $3/1.2 = 2.50$, but neither the test nor the interval excludes 1. Under the hypothesis that the cohort's rates are the standard rates, the count is Poisson with mean 1.2. The probabilities of 0, 1 and 2 deaths are

$$e^{-1.2} = 0.3012, \qquad 1.2\,e^{-1.2} = 0.3614, \qquad \frac{1.2^2}{2}\,e^{-1.2} = 0.2169,$$

so $P(D \ge 3) = 1 - 0.3012 - 0.3614 - 0.2169 = 0.1205$. Doubled, the two-sided p-value is 0.241. The exact limits for a count of 3 are $G^{-1}_{3}(0.025) = 0.619$ and $G^{-1}_{4}(0.975) = 8.767$, so the interval for the SMR is $(0.619/1.2,\ 8.767/1.2) = (0.52,\ 7.31)$.

Three deaths against 1.2 expected is two and a half times the expectation, and it is still an outcome that the standard rates produce about one time in eight. The log-scale interval, $2.50 \times e^{\pm 1.96/\sqrt{3}} = (0.81,\ 7.75)$, should not be used at a count this small: its lower limit is more than half again the exact one.

What we have learned

Indirect standardization compares observed with expected deaths. Its SMR is stable for small populations but compares each one only with the standard. By both methods, Alaska's mortality in 2021 was higher than Maine's once age is taken into account.

Both methods rest on the same move: averaging rates over groups with a chosen set of weights. In the language of probability, that move is the law of total probability. The next unit, Probability, begins with The Rules of Probability. Its second article, Conditional Probability and the Law of Total Probability, returns to crude and standardized rates in those terms.

In Python

from scipy import stats

def smr(observed, expected, level=0.95):
    a = (1 - level) / 2
    lo = stats.gamma.ppf(a, observed) / expected
    hi = stats.gamma.ppf(1 - a, observed + 1) / expected
    return observed / expected, (lo, hi)

print(smr(6208, 5854.3))   # Alaska: 1.0604, (1.0342, 1.0871)
print(smr(12, 7.5))        # 1.6, (0.827, 2.795)

Every number in this article is computed by tools/experiments/applied-statistics/direct-and-indirect-standardization.py in the site's repository, the script it shares with Direct Standardization. The script queries CDC WONDER and the Census estimates and asserts the standardized mortality ratios and intervals quoted here.

References

  • Anderson, R. N., and Rosenberg, H. M. (1998). Age standardization of death rates: Implementation of the year 2000 standard. National Vital Statistics Reports, 47(3). National Center for Health Statistics. record · 4 pages
  • Breslow, N. E., and Day, N. E. (1987). Statistical Methods in Cancer Research, Volume II: The Design and Analysis of Cohort Studies, Chapter 2 (Rates and rate standardization). IARC Scientific Publications No. 82. International Agency for Research on Cancer. record · 5 pages
  • Centers for Disease Control and Prevention, National Center for Health Statistics. Underlying Cause of Death 1999–2020, CDC WONDER online database, from the Multiple Cause of Death Files compiled through the Vital Statistics Cooperative Program. https://wonder.cdc.gov/ucd-icd10.html (queried November 2026). record · 3 pages
  • Kilpatrick, S. J. (1963). Mortality comparisons in socio-economic groups. Applied Statistics, 12(2), 65–86. Cited as Breslow and Day (1987) cite it. record
  • Murphy, S. L., Kochanek, K. D., Xu, J., and Arias, E. (2024). Deaths: Final data for 2021. National Vital Statistics Reports, 73(8). National Center for Health Statistics. Tables 2 and 17. record · 6 pages
  • Pagano, M., Gauvreau, K., and Mattie, H. (2022). Principles of Biostatistics (3rd ed.). CRC Press. The course text. record · 48 pages
  • U.S. Census Bureau, Population Division (2022). Annual State Resident Population Estimates for 6 Race Groups (5 Race Alone Groups and Two or More Races) by Age, Sex, and Hispanic Origin: April 1, 2020 to July 1, 2021 (Vintage 2021; released June 2022), file sc-est2021-alldata6. https://www2.census.gov/programs-surveys/popest/datasets/2020-2021/state/asrh/ record · 5 pages